UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Reduced Memory Region Based Deep Convolutional Neural Network Detection

Tome', D; Bondi, L; Plebani, E; Baroffio, L; Pau, D; Tubaro, S; (2016) Reduced Memory Region Based Deep Convolutional Neural Network Detection. In: 2016 IEEE 6th International Conference on Consumer Electronics - Berlin (ICCE-Berlin). IEEE: Berlin, Germany. Green open access

[thumbnail of 1609.02500v1.pdf]
Preview
Text
1609.02500v1.pdf - Accepted Version

Download (417kB) | Preview

Abstract

Accurate pedestrian detection has a primary role in automotive safety: for example, by issuing warnings to the driver or acting actively on car's brakes, it helps decreasing the probability of injuries and human fatalities. In order to achieve very high accuracy, recent pedestrian detectors have been based on Convolutional Neural Networks (CNN). Unfortunately, such approaches require vast amounts of computational power and memory, preventing efficient implementations on embedded systems. This work proposes a CNN-based detector, adapting a general-purpose convolutional network to the task at hand. By thoroughly analyzing and optimizing each step of the detection pipeline, we develop an architecture that outperforms methods based on traditional image features and achieves an accuracy close to the state-of-the-art while having low computational complexity. Furthermore, the model is compressed in order to fit the tight constrains of low power devices with a limited amount of embedded memory available. This paper makes two main contributions: (1) it proves that a region based deep neural network can be finely tuned to achieve adequate accuracy for pedestrian detection (2) it achieves a very low memory usage without reducing detection accuracy on the Caltech Pedestrian dataset.

Type: Proceedings paper
Title: Reduced Memory Region Based Deep Convolutional Neural Network Detection
Event: 2016 IEEE 6th International Conference on Consumer Electronics
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/ICCE-Berlin.2016.7684706
Publisher version: http://dx.doi.org/10.1109/ICCE-Berlin.2016.7684706
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: cs.CV, cs.CV
UCL classification: UCL
UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10123188
Downloads since deposit
Loading...
46Downloads
Download activity - last month
Loading...
Download activity - last 12 months
Loading...
Downloads by country - last 12 months
Loading...

Archive Staff Only

View Item View Item